Abstract
Lung neuroendocrine tumor is a special kind of lung cancer. The level of tumor is a major factor in the diagnostic process of this kind of tumor, where Ki-67 proliferation is often used as the classification index. The segmentation and classification of Ki-67 immunohistochemical images of lung neuroendocrine tumors is the key to realize automatic calculation of Ki-67 proliferation index. In this paper, a new image segmentation algorithm based on double layer watershed is proposed, which is suitable for the characteristics of uneven color of the nucleus. For calculating the Ki-67 proliferation index, classification of negative and positive tumor cells by their color difference is accomplished. By means of the features of regional average gray level, area and circularity, the segmentation of nucleus which cannot be completely segmented is supplemented. The mean and standard deviation are used to evaluate the accuracy after segmentation, and they have major improvement through the new algorithm proposed in this paper. Detailed theoretical analysis and reasonable experimental results demonstrate the feasibility and accuracy of the method.
Similar content being viewed by others
References
Ao J, Mitra S, Long R, Nutter B, Antani S (2012) A hybrid watershed method for cell image segmentation. Proc IEEE Southwest Symp Imag Anal Interpret (SSIAI: 29–32. doi:10.1109/SSIAI.2012.6202445
Caves R, Quegan S, White R (1998) Quantiative comparison of the performance of SAR segmentation algorithms. IEEE Trans Image Process 7(11):1534–1536
Chen W et. al. (2016) Cancer statistics in China. CA: A Cancel J Clin. 66(2): 115–132. https://doi.org/10.3322/caac.21338
Chen S, Suzuki K, MacMahon H (2011) Development and evaluation of a computer-aided diagnostic scheme for lung nodule detection in chest radiographs by means of two-stage nodule enhancement with support vector classification. Med Phys 38(4):1844–1858. https://doi.org/10.1118/1.3561504
Cherni MA, Sayadi M, Fnaiech F (2009) Using granulometry and watershed for breast tumor cells segmentation. Proc Int Conf Sign Circ Syst (SCS): 1–5. https://doi.org/10.1109/ICSCS.2009.5412539
Devaki K, Bhaskaran VM, Suphalakshmi A (2014) FastWatersnakes: an improved image segmentation framework. Imag Sci J 62(6):303–312. https://doi.org/10.1179/1743131X13Y.0000000066
Fan D, Wei L, Cao M (2016) Extraction of target region in lung immunohistochemical image based on artificial neural network. Multimed Tools Appl 75(19):12227–12244. https://doi.org/10.1007/s11042-016-3459-2
Frucci M, Nappi M, Riccio D, Baja GS (2016) WIRE: watershed based iris recognition. Pattern Recogn 56:148–159. https://doi.org/10.1016/j.patcog.2015.08.017
Hunter LA, Krafft S, Stingo F et al (2013) High quality machine-robust image features: Identification in nonsmall cell lung cancer computed tomography images. Med Phys 40(12):121916. https://doi.org/10.1118/1.4829514
Lassen B, van Rikxoort EM, Schmidt M et al (2013) Automatic segmentation of the pulmonary lobes from chest CT scans based on fissures, vessels, and bronchi. IEEE Trans Med Imag 32(2):210–222. https://doi.org/10.1109/TMI.2012.2219881
Liu BH, Wang WZ, Fang XD (2006) Automatic extraction of positive cells in tumor Immunohistochemical pathology image based on YCbCr. Proc World Congress Intell Contrl Auto (WCICA) 2:9708–9712. https://doi.org/10.1109/WCICA.2006.1713888
Lu S, Wang S, Zhang Y (2017) A note on the marker-based watershed method for X-ray image segmentation. Comput Methods Prog Biomed 141:1–2. https://doi.org/10.1016/j.cmpb.2017.01.014
Mouelhi A, Sayadi M, Fnaiech F, Mrad K, Romdhane KB (2013) Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method. Biomed Sign Process Contrl 8(5):421–436. https://doi.org/10.1016/j.bspc.2013.04.003
Movsas B, Moughan J, Komaki R et al (2003) Radiotherapy patterns of care study in lung carcinoma. J Clin Oncol 21(24):4553–4559. https://doi.org/10.1200/JCO.2003.04.018
Ng A, Nguyen T, Moseley JL et al (2010) Reconstruction of 3D lung models from 2D planning data sets for Hodgkin's lymphoma patients using combined deformable image registration and navigator channels. Med Phys 37(3):1017–1028. https://doi.org/10.1118/1.3284368
Nielsen PS, Bentzer NK, Jensen V et al (2014) Immunohistochemical Ki-67/KL1 double stains increase accuracy of Ki-67 indices in breast cancer and simplify automated image analysis.[J]. Appl Immunohistochem Molec Morphol Aimm 22(8):568–576
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybernet 9(1):62–66. https://doi.org/10.1109/TSMC.1979.4310076
Qi X, Xing F, Foran DJ et al (2012) Robust segmentation of overlapping cells in histopathology specimens using parallel seed detection and repulsive level set. IEEE Trans Biomed Eng 59(3):754–765. https://doi.org/10.1109/TBME.2011.2179298
Rakovich TY, Mahfoud OK, Mohamed BM et al (2014) Highly sensitive single domain antibody-quantum dot conjugates for detection of HER2 biomarker in lung and breast cancer cells. ACS Nano 8(6):5682–5695
Sa J, Sun X, Zhang T, Li H, Zeng H (2016) Improved Otsu segmentation based on sobel operator. 3rd Int Conf Syst Inform (ICSAI): 886–890. doi:https://doi.org/10.1109/ICSAI.2016.7811076
Schuffler PJ, Schapiro D, Giesen C et al (2015) Automatic single cell segmentation on highly multiplexed tissue images. Cytometry, Part A 87(10):936–942. https://doi.org/10.1002/cyto.a.22702
Shi Y, Gao Y, Wang R et al (2013) Transductive cost-sensitive lung cancer image classification. Appl Intell 38(1):16–28. https://doi.org/10.1007/s10489-012-0354-z
Tan Y, Schwartz LH, Zhao B (2013) Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field. Med Phys 40(4):043502–043502. https://doi.org/10.1118/1.4793409
Vitulano S, Di Ruberto C, Nappi M (1997) Different methods to segment biomedical images. Pattern Recogn Lett 18(11–13):1125–1131. https://doi.org/10.1016/S0167-8655(97)00097-4
Wei Q, Hu Y, MacGregor J (2008) Segmentation of lung lobes in clinical CT images. Int J Comput Assist Radiol Surg 3(1–2):151–163. https://doi.org/10.1007/s11548-008-0153-5
Wu G, Lian J, Shen D (2012) Improving image-guided radiation therapy of lung cancer by reconstructing 4D-CT from a single free-breathing 3D-CT on the treatment day. Med Phys 39(12):7694–7709. https://doi.org/10.1118/1.4768226
Xie X, Livermore C (2017) Passively self-aligned assembly of compact barrel hinges for high-performance, out-of-plane mems actuators. IEEE 30th Int Conf Micro Electro Mech Syst (MEMS): 813–816. https://doi.org/10.1109/MEMSYS.2017.7863532
Xie X, Zaitsev Y, Velásquez-García LF, Teller SJ, Livermore C (2014) Scalable, MEMS-enabled, vibrational tactile actuators for high resolution tactile displays. J Micromech Microeng 24(12):125014. https://doi.org/10.1088/0960-1317/24/12/125014
Xing F, Su H, Neltner J et al (2014) Automatic Ki-67 counting using robust cell detection and online dictionary learning. IEEE Trans Biomed Eng 61(3):859–870. https://doi.org/10.1109/TBME.2013.2291703
Xing F, Xie Y, Yang L (2016) An automatic learning-based framework for robust nucleus segmentation. IEEE Trans Med Imaging 35(2):550–566. https://doi.org/10.1109/TMI.2015.2481436
Xue Z, Wong K, Wong STC (2010) Joint registration and segmentation of serial lung CT images for image-guided lung cancer diagnosis and therapy. Comput Med Imaging Graph 34(1):55–60. https://doi.org/10.1016/j.compmedimag.2009.05.007
Yang H, Ahuja N (2013) Automatic segmentation of granular objects in images: combining local density clustering and gradient-barrier watershed. Pattern Recogn 47(6):2266–2279. https://doi.org/10.1016/j.patcog.2013.11.004
Zhang YD, Wu LN (2009) Segment-based coding of color images. Sci Chin Ser F: Inform Sci 52(6):914–925. https://doi.org/10.1007/s11432-009-0019-7
Zhang Y, Dong Z, Phillips P, Wang S, Ji G, Yang J (2015) Exponential wavelet iterative shrinkage thresholding algorithm for compressed sensing magnetic resonance imaging. Inf Sci 322:115–132. https://doi.org/10.1016/j.ins.2015.06.017
Zhang L, Sonka M, Lu L, Summers RM, Yao J (2017) Combining fully convolutional networks and graph-based approach for automated segmentation of cervical cell nuclei. Proc 14th IEEE Int Symp Biomed Imag: 406–409. doi:https://doi.org/10.1109/ISBI.2017.7950548
Zijdenbos AP, Dawant BM, Margolin RA, Palmer AC (1994) Morphometric analysis of white matter lesions in MR images: method and validation. IEEE Trans Med Imaging 13(4):716–724. https://doi.org/10.1109/42.363096
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cao, M., Wang, S., Wei, L. et al. Segmentation of immunohistochemical image of lung neuroendocrine tumor based on double layer watershed. Multimed Tools Appl 78, 9193–9215 (2019). https://doi.org/10.1007/s11042-018-6431-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6431-5